4978c0d0cd
Hostile audit of the original report flagged three load-bearing errors:
1. held_tokens semantic was inverted. session_held_tokens() at
session_aware_cache.py:278-282 sums (kv_allocated_len - cache_protected_len)
per slot, i.e. slot-private (NOT in radix tree). So "other = cap - held -
avail" actually CONTAINS the radix-tree protected prefix cache (likely the
single biggest component for shared agentic prefixes), not just running
batch + in-flight as the original report claimed.
2. Admission-race causal hypothesis for the 415 EXP2+profile errors is
contradicted by the data: 414/415 errors have kv_transfer_blocks > 0 — they
passed admission and died downstream ("generate stream ended before
producing any token", raised by the client when a 200 response had an empty
stream).
3. Polling deconfound was too quickly dismissed. Mode counts shift ~1:1
(session-cap-fb -356 / kvcache-centric +406), and /server_info is not a
passive read — it dispatches into the scheduler main loop and iterates
every session slot.
Plus: per-D error% confounded by sticky session affinity (only 18 unique
sessions cause 415 errors, decode-3 had 0 errors only because no high-error
session landed there); decile 10 "recovery" was an equal-time binning
artifact (24.5% under equal-count); v5 vs v5+profile time gap was 21h not
6h; p50/p90 latency comparison is N=1.
Rewritten report (docs/V5_PROFILE_INVESTIGATION_ZH.md) marks each correction
with ⚠️ and demotes admission-race to one of four hypotheses (H1-H4).
Action items split into P0 (verify, must do first) and P1 (instrument):
P0 — scripts/sweep_tp1_v5_baseline_rerun_exp2.sh runs 3x v5 baseline EXP2
(no polling, identical config to the original v5 run) to test whether the
9-error baseline result is reproducible. If 3 runs give ~9 errors and
profile gives 415, polling is the leading suspect. Currently running
in background.
P1 — scheduler.py:_compute_pool_breakdown_for_diagnostics adds a read-only
"pool_breakdown" dict to /server_info covering: radix_evictable_tokens,
radix_protected_tokens, slot_private_held_tokens, session_slot_count,
running_batch_{reqs,kv_tokens}, transfer_queue_{reqs,tokens},
prealloc_queue_{reqs,tokens}, retracted_queue_{reqs,tokens}. With these,
"unaccounted = cap - sum(known)" exposes true leakage. replay.py captures
all fields into the per-tick row; analyzer prints the decomposition and
gracefully handles old timeseries (prints "P1 instrument absent").
Mock-tested end-to-end. SGLang patch is read-only and does not affect
admission/scheduling. Old v5+profile data still analyzes correctly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Agentic PD Hybrid
这个项目是在 SGLang xPyD 上做一个最小实验框架，用来判断：
面向 agentic coding workload 的 session-aware / KV-cache-aware P/D routing，能不能降低端到端延迟。
更完整但仍然简洁的说明见 docs/PROJECT_OVERVIEW.md。
当前做了什么
- 启动单机 SGLang P/D 栈。
- 回放 Ali coding agent trace，并记录 request-level metrics。
- 支持
default、sticky、kv-aware路由策略。 - 支持
pd-disaggregation、kvcache-centric、pd-colo对比。 - 支持小 append、多轮 session 的 micro-benchmark trace。
- 维护了基于 SGLang
v0.5.10的本地 patch，放在third_party/sglang。
环境
统一使用 uv：
uv sync
默认模型路径：
~/models/Qwen/Qwen3-Coder-30B-A3B-Instruct
当前主要测试环境是单机 8 GPU，约束是 prefill + decode <= 8。
常用命令
生成小 append trace：
uv run agentic-pd-hybrid make-small-append-trace \
--output outputs/smoke-hotcap-30k-1k-256.jsonl \
--session-count 4 \
--turns-per-session 3 \
--initial-input-length 30000 \
--append-input-length 1000 \
--output-length 256
跑 live benchmark：
uv run agentic-pd-hybrid benchmark-live \
--trace outputs/micro-serveable-varturn-30k-1k-256-20260424T0756Z.jsonl \
--output-root outputs/live-serveable-varturn-30k-1k-256-hotcap \
--mechanism kvcache-centric \
--policy kv-aware \
--kvcache-admission-mode worker \
--prefill-workers 1 \
--decode-workers 1 \
--prefill-gpu-ids 0 \
--decode-gpu-ids 1 \
--transfer-backend mooncake \
--target-duration-s 2000 \
--session-sample-rate 1.0 \
--min-turns 2 \
--time-scale 1 \
--concurrency-limit 1000
只回放并写 metrics：
uv run agentic-pd-hybrid replay \
--trace path/to/trace.jsonl \
--policy kv-aware \
--mechanism pd-disaggregation \
--router-url http://127.0.0.1:8000 \
--output outputs/replay.jsonl
输出
每次 replay/benchmark 会写：
- request metrics：
request-metrics.jsonl - 汇总结果：
request-metrics.jsonl.summary.json
重点看：
- E2E latency
- TTFT / TPOT
- execution mode
- cached tokens
- KV transfer blocks
- error
维护约定
- 项目代码改动：
feat:/fix:/docs:。 - SGLang 改动：
feat(sglang): .../fix(sglang): ...。 third_party/sglang的基线是 clean SGLangv0.5.10snapshot。- 不提交
outputs/、日志、__pycache__、虚拟环境。